import matplotlib.pyplot as plt
%matplotlib inline

import numpy as np
import pandas as pd
import pickle

import helper
from IPython.display import display, HTML
import seaborn as sns

df_orig = helper.get_data()

df_orig.shape

(18110, 20)

25 clusters

# 21 (18 clusters), 28 (22 clusters), 41 (25 clusters) - dataset1 (without 01)
df = helper.get_cluster_df(df_orig, idx = 41, expected_cluster = 25)

/home/nandy/repository/bit/agp/helper.py:110: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.
  df_fossil = df_fossil.groupby(['clust'])['fossil','green'].sum().sort_values('fossil', ascending = False)

Avg energy shares

fuel_cols = ['wind', 'solar', 'solar_rooftop','blackcoal', 'browncoal','gas','diesel','kerosene','hydro','bagasse','batterys', 'net_import']
additional_cols = ['demand', 'rrp', 'export']

pd.set_option('display.max_columns', 200)
pd.set_option('display.max_rows', 100)
pd.set_option('display.min_rows', 100)
pd.set_option('display.expand_frame_repr', True)

X = df[['clust'] + fuel_cols]
X = X.groupby(['clust']).agg(['mean', 'std']).reset_index().apply(lambda x: round(x, 2))
X = X.rename(columns = {'clust' : 'cluster'})
with pd.option_context('display.max_rows', None, 'display.max_columns', None): 
    display(HTML(X.to_html(index = False))) 

cluster	wind		solar		solar_rooftop		blackcoal		browncoal		gas		diesel		kerosene		hydro		bagasse		batterys		net_import
	mean	std	mean	std	mean	std	mean	std	mean	std	mean	std	mean	std	mean	std	mean	std	mean	std	mean	std	mean	std
1	0.00	0.00	0.00	0.00	0.00	0.00	78.83	4.50	0.00	0.00	19.15	4.42	0.00	0.00	0.00	0.01	1.37	0.75	0.63	0.54	0.00	0.00	0.02	0.12
2	0.00	0.00	0.01	0.04	1.17	1.97	78.62	4.62	0.00	0.00	17.49	4.95	0.00	0.00	0.42	0.47	1.41	0.88	0.43	0.41	0.00	0.00	0.44	0.88
3	4.49	3.47	0.00	0.00	0.00	0.00	0.00	0.00	88.14	5.35	2.38	2.41	0.00	0.00	0.00	0.00	4.96	3.51	0.00	0.00	0.00	0.00	0.02	0.12
4	0.73	1.00	2.38	2.18	5.26	1.68	79.80	4.98	0.00	0.00	10.01	3.51	0.00	0.00	0.00	0.00	1.40	0.71	0.40	0.35	0.00	0.00	0.01	0.07
5	0.79	0.59	3.19	1.50	5.04	1.60	78.13	4.33	0.00	0.00	10.14	2.74	0.00	0.01	0.18	0.18	1.83	0.76	0.30	0.27	0.00	0.00	0.40	0.99
6	2.09	1.82	0.10	0.26	0.24	0.69	80.49	4.31	0.00	0.00	5.65	2.16	0.35	0.07	0.00	0.00	3.92	2.07	0.00	0.00	0.00	0.00	7.15	4.02
7	1.54	1.49	0.14	0.27	0.00	0.00	78.84	6.25	0.00	0.00	5.24	1.95	0.00	0.00	0.00	0.00	3.50	2.37	-0.00	0.00	0.00	0.00	10.73	5.41
8	8.17	5.54	0.03	0.06	2.76	1.19	0.00	0.00	79.75	6.16	4.25	4.10	0.00	0.00	0.00	0.00	4.99	3.61	0.00	0.00	0.00	0.00	0.06	0.26
9	5.35	4.21	0.04	0.09	1.83	1.89	0.00	0.00	74.95	8.41	6.25	4.54	0.00	0.00	0.00	0.00	6.61	3.55	0.00	0.00	0.00	0.00	4.97	2.79
10	4.62	3.00	1.61	0.93	3.42	1.46	77.82	6.27	0.00	0.00	2.42	2.15	0.00	0.00	0.00	0.00	3.59	1.97	-0.00	0.00	0.00	0.00	6.52	4.44
11	3.63	2.53	1.06	0.78	2.38	1.83	72.08	7.32	0.00	0.00	5.10	2.52	0.01	0.02	0.03	0.03	5.32	3.00	0.00	0.00	0.00	0.00	10.38	5.08
12	12.42	6.78	1.34	0.57	5.20	1.97	0.00	0.00	73.94	5.84	3.22	3.11	0.00	0.00	0.00	0.00	3.71	2.72	0.00	0.00	0.04	0.02	0.13	0.39
13	8.97	6.13	1.21	0.53	4.03	1.93	0.00	0.00	65.70	6.69	7.42	4.37	0.00	0.00	0.00	0.00	6.04	3.52	0.00	0.00	0.05	0.02	6.57	3.51
14	15.32	NaN	0.00	NaN	0.00	NaN	0.00	NaN	26.49	NaN	39.15	NaN	1.43	NaN	0.00	NaN	0.00	NaN	0.00	NaN	0.00	NaN	17.61	NaN
15	23.52	14.44	0.00	0.00	0.00	0.00	0.00	0.00	18.60	10.41	43.26	11.31	0.17	0.18	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	14.45	11.01
16	29.40	16.76	0.00	0.00	0.00	0.00	0.00	0.00	19.39	10.28	39.83	11.62	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	11.38	10.34
17	23.41	12.20	1.04	1.46	7.96	5.11	0.00	0.00	0.27	1.91	56.40	11.38	0.96	0.86	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	9.96	9.96
18	25.91	12.02	3.40	1.92	11.61	5.36	0.00	0.00	0.00	0.00	53.14	10.79	0.41	0.27	0.00	0.00	0.00	0.00	0.00	0.00	0.11	0.06	5.41	6.89
19	26.18	13.85	3.17	1.64	11.34	4.99	0.00	0.00	0.00	0.00	47.34	14.49	0.01	0.02	0.00	0.00	0.00	0.00	0.00	0.00	0.04	0.05	11.93	7.72
20	34.54	18.35	0.00	0.02	6.63	4.09	0.00	0.00	0.00	0.00	46.28	15.15	0.04	0.06	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	12.51	12.86
21	45.75	18.08	2.60	1.42	9.62	4.43	0.00	0.00	0.00	0.00	41.92	16.75	0.02	0.04	0.00	0.00	0.00	0.00	0.00	0.00	0.04	0.05	0.06	0.26
22	7.43	5.49	0.00	0.00	0.76	0.88	0.00	0.00	0.00	0.00	17.05	3.96	0.00	0.00	0.00	0.00	60.40	14.24	0.00	0.00	0.00	0.00	14.35	12.31
23	5.10	4.08	0.00	0.00	0.00	0.01	0.00	0.00	0.00	0.00	14.06	3.67	0.00	0.00	0.00	0.00	80.78	6.10	0.00	0.00	0.00	0.00	0.06	0.19
24	10.09	6.42	0.00	0.00	0.89	1.10	0.00	0.00	0.00	0.00	0.72	1.33	0.00	0.00	0.00	0.00	66.17	13.98	0.00	0.00	0.00	0.00	22.13	12.69
25	9.04	5.53	0.00	0.00	0.63	0.76	0.00	0.00	0.00	0.00	0.63	1.07	0.00	0.00	0.00	0.00	89.67	5.64	0.00	0.00	0.00	0.00	0.04	0.14

X = df[['clust'] + additional_cols]
X = X.groupby(['clust']).agg(['mean', 'std']).reset_index().apply(lambda x: round(x, 2))
X = X.rename(columns = {'clust' : 'cluster'})
with pd.option_context('display.max_rows', None, 'display.max_columns', None): 
    display(HTML(X.to_html(index = False))) 

cluster	demand		rrp		export
	mean	std	mean	std	mean	std
1	141655.59	9309.28	42.53	19.94	12087.25	7244.41
2	160156.66	15318.19	126.29	193.69	6700.23	7075.08
3	133180.33	13331.62	39.22	22.64	15605.51	9717.94
4	159693.26	12114.22	67.13	22.97	14572.51	6711.84
5	164824.64	14676.17	76.90	31.69	11811.98	8331.80
6	191580.08	14076.02	57.18	12.64	29.39	251.10
7	196706.05	17922.68	43.43	21.57	19.89	293.02
8	125145.06	12425.02	79.64	50.38	13593.15	11994.16
9	138416.17	14691.02	88.30	58.44	27.44	428.13
10	199191.90	17425.48	75.52	26.39	404.01	1658.92
11	211972.99	24378.54	177.08	277.43	74.12	741.23
12	123318.78	11571.64	69.39	63.42	7571.75	6732.44
13	132259.72	12770.56	115.85	235.86	56.16	627.12
14	33977.00	NaN	52.56	NaN	0.00	NaN
15	39485.87	5907.59	84.83	73.71	373.70	1183.43
16	36690.27	4598.20	42.24	20.08	533.97	1360.94
17	42278.96	8075.17	312.11	462.70	867.01	2072.90
18	44377.62	10978.07	198.23	246.10	554.26	1344.91
19	37703.66	4934.91	78.30	31.22	0.00	0.00
20	36698.74	4364.18	89.77	31.91	1779.57	3172.63
21	37465.38	3841.35	64.76	39.39	4455.69	3112.78
22	28230.67	2203.46	79.72	57.92	553.48	1915.27
23	29183.58	2657.03	49.02	40.28	5427.92	3970.16
24	28559.48	2048.81	62.29	34.11	0.00	0.00
25	31036.14	2270.82	55.85	33.62	5248.21	3763.37

Cluster distribution

helper.plot_cluster_percentages(df, reorder = True)

clust	count	percentage
7	2120	11.71
3	2056	11.35
1	1928	10.65
16	1785	9.86
10	1332	7.36
4	1254	6.92
25	1224	6.76
23	859	4.74
24	782	4.32
22	757	4.18
20	620	3.42
21	538	2.97
8	475	2.62
12	439	2.42
2	380	2.10
9	366	2.02
15	323	1.78
13	286	1.58
19	238	1.31
17	101	0.56
11	100	0.55
6	73	0.40
5	57	0.31
18	16	0.09
14	1	0.01

Cluster distribution by state

t = helper.get_cluster_state_shares(df)
print(t)

state    NSW1    QLD1     SA1    TAS1    VIC1
clust                                        
1         0.0  1928.0     0.0     0.0     0.0
2         0.0   380.0     0.0     0.0     0.0
3         0.0     0.0     0.0     0.0  2056.0
4         1.0  1253.0     0.0     0.0     0.0
5         0.0    57.0     0.0     0.0     0.0
6        73.0     0.0     0.0     0.0     0.0
7      2118.0     2.0     0.0     0.0     0.0
8         0.0     0.0     0.0     0.0   475.0
9         0.0     0.0     0.0     0.0   366.0
10     1330.0     2.0     0.0     0.0     0.0
11      100.0     0.0     0.0     0.0     0.0
12        0.0     0.0     0.0     0.0   439.0
13        0.0     0.0     0.0     0.0   286.0
14        0.0     0.0     1.0     0.0     0.0
15        0.0     0.0   323.0     0.0     0.0
16        0.0     0.0  1785.0     0.0     0.0
17        0.0     0.0   101.0     0.0     0.0
18        0.0     0.0    16.0     0.0     0.0
19        0.0     0.0   238.0     0.0     0.0
20        0.0     0.0   620.0     0.0     0.0
21        0.0     0.0   538.0     0.0     0.0
22        0.0     0.0     0.0   757.0     0.0
23        0.0     0.0     0.0   859.0     0.0
24        0.0     0.0     0.0   782.0     0.0
25        0.0     0.0     0.0  1224.0     0.0

Cluster plot by state and individual days

X = df[['state', 'year', 'month', 'day', 'clust', 'probs']]
X = helper.get_cluster_assignment_day(X)

months=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sept', 'Oct', 'Nov', 'Dec']
X.loc[:,'month'] = pd.Categorical(X['month'].map(lambda x: months[x-1]), categories=months, ordered=True)

X = X.pivot_table(index = ['state', 'month'], columns =['year', "day"], values = "clust")

# years = ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October', 'November', 'December']
years = list(range(2010, 2021))
fig, ax = plt.subplots(11, 1, figsize=(10, 48))
for idx in range(0, 11):
    d = X.loc['NSW1'][years[idx]]
    g = sns.heatmap(d,annot=True, vmin = 1, vmax = 25, 
                    yticklabels=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sept', 'Oct', 'Nov', 'Dec'],
                    linewidths=.5, cmap="YlGnBu", ax = ax[idx], cbar = False,
                   mask = d.isnull())
    g.set_yticklabels(g.get_yticklabels(), rotation = 0, fontsize = 8)
    ax[idx].set_xlabel('Time (in days)')
    ax[idx].set_ylabel('{}'.format(years[idx]))
    ax[idx].xaxis.label.set_size(12)
    ax[idx].yaxis.label.set_size(12)

years = list(range(2010, 2021))
fig, ax = plt.subplots(11, 1, figsize=(10, 48))
for idx in range(0, 11):
    d = X.loc['NSW1'][years[idx]].dropna()
    g = sns.heatmap(d,annot=True, vmin = 1, vmax = 25, 
#                     yticklabels=['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sept', 'Oct', 'Nov', 'Dec'],
                    linewidths=.5, cmap="YlGnBu", ax = ax[idx], cbar = False)
#                    mask = X.loc['NSW1'][years[idx]].isnull())
    g.set_yticklabels(g.get_yticklabels(), rotation = 0, fontsize = 8)
    ax[idx].set_xlabel('Time (in days)')
    ax[idx].set_ylabel('{}'.format(years[idx]))
    ax[idx].xaxis.label.set_size(12)
    ax[idx].yaxis.label.set_size(12)

Cluster plot by state and months

X.head()

	year	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020
state	month
NSW1	1	NaN	7.0	7.0	7.0	7.0	7.0	7.0	10.0	10.0	10.0	10.0
	2	NaN	7.0	7.0	7.0	7.0	7.0	7.0	10.0	10.0	10.0	10.0
	3	NaN	7.0	7.0	7.0	7.0	7.0	7.0	10.0	10.0	10.0	10.0
	4	NaN	7.0	7.0	7.0	7.0	7.0	7.0	10.0	10.0	10.0	10.0
	5	NaN	7.0	7.0	7.0	7.0	7.0	7.0	10.0	10.0	10.0	10.0

X = df[['datetime', 'state', 'year', 'month', 'clust', 'probs']]
X = helper.get_cluster_assignment_month(X)

print('unique clusters {}'.format(np.sort(X['clust'].unique())))

X = X.pivot_table(index = ['state', 'month'], columns = "year", values = "clust")
fig, ax = plt.subplots(figsize=(10, 20))  

sns.heatmap(X,annot=True, vmin = 1, vmax = 25, 
            linewidths=.5, cmap="YlGnBu", ax = ax, cbar = False)

plt.ylabel('State - Month', fontsize = 12)
plt.xlabel('Time (in years)', fontsize = 12)

/home/nandy/repository/git/p3_venv/lib/python3.6/site-packages/pandas/core/indexing.py:1596: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  self.obj[key] = _infer_fill_value(value)
/home/nandy/repository/git/p3_venv/lib/python3.6/site-packages/pandas/core/indexing.py:1743: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  isetter(ilocs[0], value)

unique clusters [ 1  2  3  4  6  7  8  9 10 11 12 13 16 17 19 20 21 22 23 24 25]

Text(0.5, 159.0, 'Time (in years)')

Demand

fig, ax = plt.subplots(figsize=(10, 5))
X = df.copy()
# mkr_dict = {'NSW1': 'x', 'QLD1': 'v', 'SA1': 'o', 'VIC1':'^', 'TAS1' :'1'}
mkr_dict ={'NSW1': 'D', 'QLD1': 'v', 'SA1': 'o', 'VIC1':'^', 'TAS1' :'*'}
g = sns.scatterplot(x = 'datetime', y = 'demand', hue='clust_category', style='state', s = 30,
                    markers = mkr_dict, data = X, alpha = 0.5, legend='brief')

handles, labels = ax.get_legend_handles_labels()

labels = labels[1:26] + labels[27:]
handles = handles[1:26] + handles[27:]
g.legend(handles=handles, labels=labels, fontsize = 12,
        loc=4, ncol= 8, bbox_to_anchor=(1.05, -0.6), title = 'Clusters/State',title_fontsize = 12)
# legend = g.legend()
# legend.texts[0].set_text("Clusters")
# legend.texts[1].set_text("State")


# Set x-axis label
plt.xlabel('Time (in days)', fontsize = 14)
a = plt.xticks(fontsize= 14)
# Set y-axis label
plt.ylabel('Demand (MWh)', fontsize = 14)
a = plt.xticks(fontsize= 14)

t = helper.get_additional_col_month(df, 'demand')
fig, ax = plt.subplots(figsize=(10, 5))
X = t.copy()
mkr_dict ={'NSW1': 'D', 'QLD1': 'v', 'SA1': 'o', 'VIC1':'^', 'TAS1' :'*'}
g = sns.scatterplot(x = 'datetime', y = 'demand', hue='clust_category', style='state', s = 50,
                    markers = mkr_dict, data = X, alpha = 0.5, legend='brief')

handles, labels = ax.get_legend_handles_labels()
# for idx, txt in enumerate(labels):
#     print('{} - {}'.format(idx, txt))
labels = labels[1:22] + labels[23:]
handles = handles[1:22] + handles[23:]
g.legend(handles=handles, labels=labels, fontsize = 12,
        loc=4, ncol= 8, bbox_to_anchor=(1.05, -0.6), title = 'Clusters/State', title_fontsize = 12)

# Set x-axis label
plt.xlabel('Time (in days)', fontsize = 14)
a = plt.xticks(fontsize= 14)
# Set y-axis label
plt.ylabel('Demand (MWh)', fontsize = 14)
a = plt.xticks(fontsize= 14)

RRP

fig, ax = plt.subplots(figsize=(10, 5))
X = df[df.rrp>150]
mkr_dict ={'NSW1': 'D', 'QLD1': 'v', 'SA1': 'o', 'VIC1':'^', 'TAS1' :'*'}
g = sns.scatterplot(x = 'datetime', y = 'rrp', hue='clust_category', style='state', s = 50,
                    markers = mkr_dict, data = X, alpha = 0.8, legend='brief')

handles, labels = ax.get_legend_handles_labels()

labels = labels[1:26] + labels[27:]
handles = handles[1:26] + handles[27:]
g.legend(handles=handles, labels=labels, fontsize = 12,
        loc=4, ncol= 8, bbox_to_anchor=(1.05, -0.6), title = 'Clusters/State',title_fontsize = 12)

# Set x-axis label
plt.xlabel('Time (in days)', fontsize = 14)
a = plt.xticks(fontsize= 14)
# Set y-axis label
plt.ylabel('RRP', fontsize = 14)
a = plt.xticks(fontsize= 14)

t = helper.get_additional_col_month(df, 'rrp')
fig, ax = plt.subplots(figsize=(10, 5))
X = t.copy()
mkr_dict ={'NSW1': 'D', 'QLD1': 'v', 'SA1': 'o', 'VIC1':'^', 'TAS1' :'*'}
g = sns.scatterplot(x = 'datetime', y = 'rrp', hue='clust_category', style='state', s = 30,
                    markers = mkr_dict, data = X, alpha = 0.5, legend='brief')

handles, labels = ax.get_legend_handles_labels()
# for idx, txt in enumerate(labels):
#     print('{} - {}'.format(idx, txt))
labels = labels[1:22] + labels[23:]
handles = handles[1:22] + handles[23:]
g.legend(handles=handles, labels=labels, fontsize = 12,
        loc=4, ncol= 8, bbox_to_anchor=(1.05, -0.6), title = 'Clusters/State', title_fontsize = 12)

# Set x-axis label
plt.xlabel('Time (in days)', fontsize = 14)
a = plt.xticks(fontsize= 14)
# Set y-axis label
plt.ylabel('RRP', fontsize = 14)
a = plt.xticks(fontsize= 14)

Export

fig, ax = plt.subplots(5, 1, figsize=(10, 25))
X = pd.merge(df, df.groupby(['clust']).size().reset_index(name='count'), on='clust')
mkr_dict ={'NSW1': 'D', 'QLD1': 'v', 'SA1': 'o', 'VIC1':'^', 'TAS1' :'*'}
g = sns.scatterplot(x = 'datetime', y = 'export', hue='clust_category', 
                    style='state', size='count', ax = ax[0], 
                    markers = mkr_dict, data = X[X.state=='NSW1'], alpha = 0.8, legend=False)
ax[0].set_ylabel('Export - NSW1', fontsize = 14)
ax[0].set_xlabel('')


g = sns.scatterplot(x = 'datetime', y = 'export', hue='clust_category', 
                    style='state', size='count', ax = ax[1],
                    markers = mkr_dict, data = X[X.state=='QLD1'], alpha = 0.8, legend=False)
ax[1].set_ylabel('Export - QLD1', fontsize = 14)
ax[1].set_xlabel('')

g = sns.scatterplot(x = 'datetime', y = 'export', hue='clust_category', 
                    style='state', size='count', ax = ax[2],
                    markers = mkr_dict, data = X[X.state=='VIC1'], alpha = 0.8, legend=False)
ax[2].set_ylabel('Export - VIC1', fontsize = 14)
ax[2].set_xlabel('')

g = sns.scatterplot(x = 'datetime', y = 'export', hue='clust_category', 
                    style='state', size='count', ax = ax[3],
                    markers = mkr_dict, data = X[X.state=='SA1'], alpha = 0.8, legend = False)
ax[3].set_ylabel('Export - SA1', fontsize = 14)
ax[3].set_xlabel('')

g = sns.scatterplot(x = 'datetime', y = 'export', hue='clust_category', 
                    style='state', size='count', ax = ax[4],
                    markers = mkr_dict, data = X[X.state=='TAS1'], alpha = 0.8, legend='brief')
ax[4].set_ylabel('Export - TAS1', fontsize = 14)


handles, labels = ax[4].get_legend_handles_labels()

labels = labels[1:26] 
handles = handles[1:26]
g.legend(handles=handles, labels=labels, fontsize = 12,
        loc=4, ncol= 8, bbox_to_anchor=(1.0, -0.7), title = 'Clusters/State',title_fontsize = 12)

# Set x-axis label
plt.xlabel('Time (in days)', fontsize = 14)
a = plt.xticks(fontsize= 14)

t = helper.get_additional_col_month(df, 'export')
fig, ax = plt.subplots(figsize=(10, 5))
# X = t.copy()
X = pd.merge(t, t.groupby(['clust']).size().reset_index(name='count'), on='clust')
mkr_dict ={'NSW1': 'D', 'QLD1': 'v', 'SA1': 'o', 'VIC1':'^', 'TAS1' :'*'}
g = sns.scatterplot(x = 'datetime', y = 'export', hue='clust_category', style='state', size = 'count',
                    markers = mkr_dict, data = X, alpha = 0.5, legend='brief')

handles, labels = ax.get_legend_handles_labels()
# for idx, txt in enumerate(labels):
#     print('{} - {}'.format(idx, txt))
labels = labels[1:22] + labels[29:]
handles = handles[1:22] + handles[29:]
g.legend(handles=handles, labels=labels, fontsize = 12,
        loc=4, ncol= 8, bbox_to_anchor=(1.05, -0.6), title = 'Clusters/State', title_fontsize = 12)

# Set x-axis label
plt.xlabel('Time (in days)', fontsize = 14)
a = plt.xticks(fontsize= 14)
# Set y-axis label
plt.ylabel('Export', fontsize = 14)
a = plt.xticks(fontsize= 14)

2 dimensional view

Z = pd.DataFrame(pickle.load(open('models/ftz_daily_5.pkl', 'rb')))
Z = Z.rename(columns={0: "dim1", 1: "dim2"})
Z['state'] = df['state'].astype('str').astype('category')
Z['clust_category'] = df['clust_category']

g = sns.scatterplot(x="dim1", y="dim2", hue="clust_category", data=Z, edgecolors='none', alpha = 0.1)
# sns.despine(bottom=True)
g.legend(loc=4, ncol= 5, bbox_to_anchor=(1.5, -0.5))
# Set x-axis label
plt.xlabel('Dimension 1')
# Set y-axis label
plt.ylabel('Dimension 2')

Text(0, 0.5, 'Dimension 2')

import random
import warnings
warnings.filterwarnings('ignore')


SMALL_SIZE = 100
MEDIUM_SIZE = 120

energy_cols = ['wind', 'solar', 'solar_rooftop', 'blackcoal', 'browncoal','gas','diesel','kerosene','hydro','bagasse','batterys', 'net_import']
additional_cols = ['export', 'demand']

plt.rc('font', size=SMALL_SIZE)          # controls default text sizes
plt.rc('axes', titlesize=SMALL_SIZE)     # fontsize of the axes title
plt.rc('axes', labelsize=MEDIUM_SIZE)    # fontsize of the x and y labels
plt.rc('xtick', labelsize=SMALL_SIZE)    # fontsize of the tick labels
plt.rc('ytick', labelsize=SMALL_SIZE)    # fontsize of the tick labels
plt.rc('legend', fontsize=MEDIUM_SIZE, markerscale = 10)    # legend fontsize
# plt.rc('figure', titlesize=BIGGER_SIZE)  # fontsize of the figure title

# sample 15K points
Xplot = pd.DataFrame()
for s in df.state.unique():
    X_sub = df[df.state == s]
    max_sample = 5000 if X_sub.shape[0] > 5000 else X_sub.shape[0]
    X_sub = X_sub.iloc[random.sample(range(0, X_sub.shape[0]), max_sample),:]
    Xplot = pd.concat([Xplot, X_sub])
    
pp = sns.pairplot(Xplot[energy_cols + additional_cols + ['clust_category']], hue = 'clust_category', diag_kind = 'kde',
             plot_kws = {'alpha': 0.5, 'edgecolor': 'k'}, height = 10)
plt.show()